Dynamic Sensitivity for Missed Bolus Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

People with diabetes face challenges in remembering to take insulin boluses after meals, leading to potential hyperglycemic episodes due to missed doses.

Innovation Solution

A method using a computing device to analyze glucose measurements and insulin dosing information, detecting missed boluses by generating notifications and dynamically adjusting sensitivity levels based on contextual information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a fixed sensitivity level is used for detecting missed boluses, then the detection algorithm is simple to implement, but it cannot adapt to different user preferences and contexts leading to suboptimal detection accuracy

Engineering Contradiction:
Improvemissed bolus detection accuracyVSAvoiddetection algorithm complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent implements dynamic sensitivity levels that can be adjusted based on user feedback and contextual information. The system transitions from a static detection algorithm to a dynamic one that adapts its sensitivity threshold, allowing it to optimize detection accuracy for different users and situations without requiring complete algorithmic redesign

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent changes the sensitivity parameter of the detection algorithm based on user preferences and contextual factors. By adjusting this key parameter dynamically, the system achieves adaptive detection accuracy while maintaining the core detection logic, thus balancing precision improvement with acceptable complexity increase

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If high sensitivity detection is used, then missed boluses are detected more accurately, but false alarms increase causing user annoyance and potential alarm fatigue

Engineering Contradiction:
Improvemissed bolus detection accuracyVSAvoidfalse alarms
Core Design Contradiction:
Measurement precisionVSObject-generated harmful factors

Solution Approach 1:

The patent applies different sensitivity levels locally based on user preferences and contextual situations. Instead of using a uniformly high sensitivity level that causes widespread false alarms, the system tailors the detection threshold to each user's tolerance and specific context, reducing false alarms in situations where they are less acceptable while maintaining high detection accuracy where needed

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The system uses user feedback from alarm responses to adjust future detection behavior. When users indicate false alarms or correct detections, the system learns from this feedback and adjusts its sensitivity, creating a closed-loop system that reduces false alarms over time while maintaining accurate detection

Inventive Principle:
Principle #23Feedback

3Reliability

If the system provides frequent alerts for potential missed boluses, then user safety is improved, but user burden and psychological stress increase

Engineering Contradiction:
Improveuser safetyVSAvoiduser psychological burden
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The patent adjusts the alert frequency and sensitivity parameters based on user preferences and contextual information. By dynamically changing these parameters, the system optimizes the balance between providing sufficient safety alerts and minimizing psychological burden, allowing users to receive appropriate levels of notification without excessive stress

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP3991174B1Systems and methods for detecting missed bolus doses
Publication Date: 2025.04.09 ELI LILLY & CO
  • EP3991174B1 patent drawingFigure 1
  • EP3991174B1 patent drawingFigure 2
  • EP3991174B1 patent drawingFigure 3

AI summary

Methods, systems and devices are provided for dynamically adjusting sensitivity of a computer-implemented detector for detecting missed insulin boluses. The disclosed methods, systems, and devices receive glucose measurements and insulin dosing information for a user, and analyze the received information to detect whether the user may have ingested food without taking an insulin bolus. The sensitivity level of the detector may be dynamically adjusted based on contextual information regarding the user to adjust for the users context, circumstances, and/or condition. If the detector detects a possible missed bolus, the detector may generate a user notification.